Introducing: The @Every agent, the fastest way to AI-pill your company, now officially out of beta.
With personal agent use, no one can see how their teammates are working with AI. With one “company agent” in @SlackHQ, they can.
The Every agent comes loaded with the skills and workflows we use to run Every, and each person on your team gets $15 in free credits to try it.
Install @Every in @SlackHQ today: every.to/agent?utm_source=x&…
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
.@kevinroose argues that AI models should pass standard safety tests before they’re released to the public.
His comparison is pharmaceuticals: Companies have to test drugs before selling them. He wants a similar baseline for AI—and coordination that gives safety researchers time to keep up.
Watch the full interview with @NataliaZarina:
every.to/podcast/the-inside-…
1
862
An AI plugin can let you borrow the steps an expert would take.
@NataliaZarina uses Compound Engineering because she isn’t an engineer: she trusts @kieranklaassen and the team maintaining it to guide her through building a product safely and following best practices.
She sees the same value in Compound Writing, where @kplikethebird has codified her approach to writing.
Watch the full episode:
every.to/context-window/ever…
.@kevinroose worried that the history of modern AI could disappear before anyone wrote it down.
The decisions were being made inside secretive labs, behind nondisclosure agreements, in messages that might delete themselves.
He wanted to document who was in the room and how those decisions happened while the people involved could still tell the story.
Watch the full interview with @NataliaZarina:
every.to/podcast/the-inside-…
3
3
1,308
.@fredgraver gives his AI collaborators different jobs.
He develops work with @claudeai, then brings it to @OpenAI’s ChatGPT—the eager film student who knows every storytelling rule—for a check on the basics.
When he needs encouragement, he turns his documents into a NotebookLM podcast. He jokes that the hosts love whatever he’s working on.
For a writer working alone, feedback and a little enthusiasm both have a place.
Watch the full episode:
every.to/context-window/ever…
1,084
Every 📧 retweeted
No more jumping to the Monologue app to dictate on iPhone.
Shipping soon. Here's a look.
Your codebase gets harder to maintain with every feature you ship. @kieranklaassen's gets easier.
He built compound engineering, and Every adopted it company-wide. The difference is compounding.
Moving a Slack attachment into Google Drive usually means downloading it, opening Drive, finding the folder, and uploading it again. Every can now upload Slack attachments straight to a Google Drive folder through its newer Drive connection.
Install Every in Slack: every.to/agent?utm_source=x&…
3
1,504
Going through a list in Slack one item at a time gets tedious when you have to type every answer. Ask the Every Agent for reply buttons, like Decision and Not a decision, and you get clickable choices right in its reply. You no longer need to set up a skill to get them.
Install Every in Slack: every.to/agent?utm_source=x&…
2
1,227
Warning on Fable 5.2: It spends a lot of time (and tokens!) on checking its work.
@hammer_mt had Fable 5.2 remake the Avengers’ epic battle of New York from Friday to Sunday and cost about $3,000 in tokens. Looking back at the logs, he found it had worked on day one, but spent the weekend play-testing and refining its work.
The tip is to start directionally on low effort, then pump it up to high or xhigh if you like the result.
Watch the full Fable 5.2 camp: every.to/events/workshop-202…
2
11
2,000
The best editors can do both line edits and coach you for your piece.
@kevinroose uses AI for line editing, but still relies on human editors for judgment, coaching, and the push to keep reporting when a story hasn’t quite come together.
Watch the full interview with @NataliaZarina:
every.to/podcast/the-inside-…
1
6
1,522
.@fredgraver asked his morning @claudeai agent to be unpleasant.
When he turns up with another idea, it reminds him what he’s already working on and what he promised to deliver. A late-night brainstorm doesn’t make tomorrow’s deadline disappear.
His AI check-in helps him keep track of commitments when a new idea threatens to pull him away.
Watch the full episode:
every.to/context-window/ever…
As AI takes on more of the building, the human thinking at the start matters even more.
@kieranklaassen sees Compound Engineering as a way to get better work out of the person using it: Ask questions, develop a strategy, push back on assumptions, and turn that thinking into work the model can execute.
The goal is to keep learning and sharpening your judgment while AI does more of the implementation.
Watch the full Fable 5.2 camp: every.to/events/workshop-202…
1
18
2,018
Opus 5.5 is our favorite model.
Here's what else the Every team is running, and who splits the big jobs from everything else.
The Daily Driver, in Context Window: every.to/context-window/micr…
Interesting find from the GPT-6.2 Astra & Sol retest: It keeps using the same grain-generating code.
@tylernishida discovered it when trying to play around with grain levels. But asking for no grain stopped it.
The repeating line is a random-number recipe from a 1992 textbook. Both models even used the same variable names and almost identical cream colours.
Our live re-test of GPT-6.2 Astra & Sol: xitter.cf/i/broadcasts/2dKOWNNpN…
1
12
2,825
BREAKING:
@Google just launched Gemini 4 Neon
We're vibe-checking live right now:
Retesting GPT-6.2 Astra & Sol xitter.cf/i/broadcasts/2dKOWNNpN…
Open invitation for anyone at @OpenAI to come on:
Retesting GPT-6.2 Astra & Sol xitter.cf/i/broadcasts/2dKOWNNpN…
This week at Every:
• @hammer_mt built map-driven autoresearch, where an agent reads a map of 104 methods and decides which experiments to run (the explainer video is made entirely in code).
• @danshipper built Galley, a word processor that checks each line against his editorial standards as he types.
• @JannikJung had Fable 5.2 design a four-channel amplifier, from choosing the parts to designing the schematic and circuit board.
• @kplikethebird shipped Every Reader, built the Wordbetter word processor, and merged her first pull request.
• The Frontier team published their vibe check for GPT-6.2 Astra and Sol, and @beckyisj and @poojary_yash spun up a live page for the new models.
• @kieranklaassen ported Everycut to Windows and Linux in one day and gave Frontier an RSS feed of all 43 published experiments.
• Andrey Galko updated Every's subscription-gifting page.
• Arielle Shipper walked 15 women through the AI coach she built to reach level eight of Every's AI adoption framework, and @elifnisapolat turned Katie's AI hot takes into a card game.
Read the experiments: frontier.every.to/?utm_sourc…
Retesting GPT-6.2 Astra & Sol xitter.cf/i/broadcasts/2dKOWNNpN…











